Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words that involve negative persuasion.

    oai_token-act-pair · gemini-2.0-flash

    deception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.66
     CreateTagHelper
    -0.59
    ModelAdmin
    -0.56
     utafitiHapana
    -0.53
    WriteTagHelper
    -0.52
    nitzel
    -0.50
    Zdroje
    -0.49
     Stande
    -0.49
    LOWER
    -0.49
    Билгалдахарш
    -0.48
    POSITIVE LOGITS
    :]:
    0.51
    providedIn
    0.50
    Portale
    0.49
    EClass
    0.49
    __*/
    0.47
    __((
    0.46
    淆
    0.46
     enga
    0.46
     mislead
    0.45
    yth
    0.45
    Act Density 0.408%

    No Known Activations